Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

robots-10

Robot Manipulation Generalization

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in robot-manipulation-generalization-10

Trend

Dataset

Best Model

Actions

The COLOSSEUM

Libraries

Use these libraries to find robot-manipulation-generalization-10 models and implementations

Datasets

RLBench

The COLOSSEUM

Subtasks

No subtasks available.

Most implemented papers

THE COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic Manipulation

Jiafei Duan, Ranjay Krishna, Wilbert Pumacay, Ishika Singh, Jesse Thomason, Dieter Fox•Mon Feb 12 2024

The COLOSSEUM is presented, a novel simulation benchmark, with 20 diverse manipulation tasks, that enables systematical evaluation of models across 14 axes of environmental perturbations, and identifies that changing the number of distractor objects, target object color, or lighting conditions are the perturbations that reduce model performance the most.

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Paper Graph

Evaluating Real-World Robot Manipulation Policies in Simulation

Sergey Levine, Oier Mees, Xuanlin Li, Kyle Hsu, Jiayuan Gu, Karl Pertsch, H. Walke, Chuyuan Fu, Ishikaa Lunawat, Isabel Sieh, Sean Kirmani, Jiajun Wu, Chelsea Finn, Hao Su, Q. Vuong, Ted Xiao•Wed May 08 2024

This work identifies control and visual disparities between real and simulated environments as key challenges for reliable simulated evaluation and proposes approaches for mitigating these gaps without needing to craft full-fidelity digital twins of real-world environments.

241 0

Paper Graph

3D Diffuser Actor: Policy Diffusion with 3D Scene Representations

Katerina Fragkiadaki, Tsung-Wei Ke, Nikolaos Gkanatsios•Thu Feb 15 2024

3D Diffuser Actor is presented, a neural policy equipped with a novel 3D denoising transformer that fuses information from the 3D visual scene, a language instruction and proprioception to predict the noise in noised 3D robot pose trajectories and its design choices dramatically outperform 2D representations, regression and classification objectives, absolute attentions, and holistic non-tokenized 3D scene embeddings.

251 0

Paper Graph

Generative Image as Action Models

Mohit Shridhar, Yat Long Lo, Stephen James•Tue Jul 09 2024

Image-generation diffusion models have been fine-tuned to unlock new capabilities such as image-editing and novel view synthesis. Can we similarly unlock image-generation models for visuomotor control? We present GENIMA, a behavior-cloning agent that fine-tunes Stable Diffusion to 'draw joint-actions' as targets on RGB images. These images are fed into a controller that maps the visual targets into a sequence of joint-positions. We study GENIMA on 25 RLBench and 9 real-world manipulation tasks. We find that, by lifting actions into image-space, internet pre-trained diffusion models can generate policies that outperform state-of-the-art visuomotor approaches, especially in robustness to scene perturbations and generalizing to novel objects. Our method is also competitive with 3D agents, despite lacking priors such as depth, keypoints, or motion-planners.

22 0

Paper Graph

Adding a benchmark result helps the community track progress.

Robot Manipulation Generalization | State-of-the-Art